| { |
| "_name_or_path": "lmsys/vicuna-13b-v1.5-16K", |
| "architectures": [ |
| "LlavaLlamaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "freeze_mm_mlp_adapter": false, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "image_aspect_ratio": "None", |
| "initializer_range": 0.02, |
| "intermediate_size": 13824, |
| "max_position_embeddings": 4096, |
| "max_sequence_length": 16384, |
| "mm_hidden_size": 72, |
| "mm_patch_merge_type": "flat", |
| "mm_projector_lr": 0.0001, |
| "mm_projector_type": "mlp2x_gelu", |
| "mm_use_im_patch_token": false, |
| "mm_use_im_start_end": false, |
| "mm_vision_select_feature": "patch", |
| "mm_vision_select_layer": -2, |
| "mm_vision_tower": "LLaSA-13B/model_4.pt", |
| "model_type": "llava_llama", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 40, |
| "num_key_value_heads": 40, |
| "pad_token_id": 0, |
| "pretraining_tp": 1, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": { |
| "factor": 4.0, |
| "type": "linear" |
| }, |
| "rope_theta": 10000.0, |
| "tie_word_embeddings": false, |
| "tokenizer_model_max_length": 2048, |
| "tokenizer_padding_side": "right", |
| "torch_dtype": "float16", |
| "transformers_version": "4.37.2", |
| "tune_mm_mlp_adapter": false, |
| "use_cache": true, |
| "use_mm_proj": true, |
| "vocab_size": 32000 |
| } |
